Neural document rerankers are extremely effective in terms of accuracy.
However, the best models require dedicated hardware for serving, which is
costly and often not feasible. To avoid this serving-time requirement, we
present a method of capturing up to 86% of the gains of a Transformer
cross-attention model with a lexicalized scoring function that only requires
10-6% of the Transformer's FLOPs per document and can be served using commodity
CPUs. When combined with a BM25 retriever, this approach matches the quality of
a state-of-the art dual encoder retriever, that still requires an accelerator
for query encoding. We introduce NAIL (Non-Autoregressive Indexing with
Language models) as a model architecture that is compatible with recent
encoder-decoder and decoder-only large language models, such as T5, GPT-3 and
PaLM. This model architecture can leverage existing pre-trained checkpoints and
can be fine-tuned for efficiently constructing document representations that do
not require neural processing of queries.

通过使用新型 scoring function 和结合 BM25 retriever 的方式，本研究证明可以使用传统 CPU 有效地构建文档排名。同时，NAIL 成为了一种可以利用预训练模型的、适用于构建文档表示的新型模型架构。

高效非自回归解码器词汇检索指数

NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive  Decoders

Interactive Fiction (IF) games are complex textual decision making problems.
This paper introduces NAIL, an autonomous agent for general parser-based IF
games. NAIL won the 2018 Text Adventure AI Competition, where it was evaluated
on twenty unseen games. This paper describes the architecture, development, and
insights underpinning NAIL's performance.

介绍 NAIL，一种适用于 general parser-based interactive fiction 游戏的自主代理，通过 2018 年 Text Adventure AI 竞赛取得胜利，文章描述了其架构、开发和性能。